PPT-CSE 486/586 Distributed Systems

Consistency 3 Steve Ko Computer Sciences and Engineering University at Buffalo Recap Consistency Linearizability Sequential consistency Chain replication Primarybackup passive replication. Concurrency Control --- 3. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Strict execution of transactions?. Delay . both their read and write operations . on an . object until . Google Chubby Lock Service. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Paxos. is a consensus algorithm.. Proposers?. Acceptors?. Learners?. A proposer always makes sure that,. Replication --- 1. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap: Concurrency Control. Extracting more concurrency. Non-exclusive locks. Two-version locking. Reducing the lock overhead. Consistency --- 3. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Consistency. Linearizability. Sequential consistency. Chain replication. Primary-backup (passive) replication. Consistency --- 2. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Linearizability. vs. Sequential Consistency. Both care about giving . an illusion of a single copy. .. From the outside observer, the system should (almost) behave as if there’s only a single copy.. Case Study: Amazon Dynamo. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. CAP Theorem?. Consistency, Availability, Partition Tolerance. Pick two. Eventual consistency?. Availability and partition tolerance over consistency. Gossiping. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recall: Passive Replication. Request Communication. : the request is issued to the primary RM and carries a unique request id.. Case Study: . Facebook Haystack. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. DNS. Hierarchical servers. Root servers, top-level domain servers, authoritative servers. CDN. Leader . Election --- 2. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Algorithm 2: Modified Ring Election . election . message tracks . all. IDs of nodes that forwarded it, not just the highest. Gossiping. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Consistency models. Linearizability. Sequential consistency. Causal consistency. Eventual consistency. Depending on application scenarios, one consistency model makes more sense that others.. Byzantine Fault . Tolerance --- 1. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Digital certificates. Binds a public key to its owner. Establishes a chain of trust. TLS. Paxos. --- 1. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. NFS. Caching with write-through policy at close(). Stateless server. One power efficient design: FAWN. Embedded CPUs & Flash . Web Content Distribution-. --3. Case Study: Facebook f4. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Engineering principle. Make the common case fast, and rare cases correct. Global States. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Last Time. Ordering of events. Many applications need it, e.g., collaborative editing, distributed storage, etc.. Logical time.